Category-specific upright orientation estimation for 3D model classification and retrieval

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 39
  • Download : 0
In this paper, we address a problem of correcting upright orientation of a reconstructed object to search. We first reconstruct an input object appearing in an image sequence, and generate a query shape using multi-view object co-segmentation. In the next phase, we utilize the Convolutional Neural Network (CNN) architecture to determine category-specific upright orientation of the queried shape for 3D model classification and retrieval. As a practical application of our system, a shape style and a pose from an inferred category and up-vector are obtained by comparing 3D shape similarity with candidate 3D models and aligning its projections with a set of 2D co-segmentation masks. We quantitatively and qualitatively evaluate the presented system with more than 720 upfront-aligned 3D models and five sets of multi-view image sequences.
Publisher
ELSEVIER
Issue Date
2020-04
Language
English
Article Type
Article
Citation

IMAGE AND VISION COMPUTING, v.96

ISSN
0262-8856
DOI
10.1016/j.imavis.2020.103900
URI
http://hdl.handle.net/10203/274168
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0